Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    The neuron activates on the boilerplate comment line “file that was distributed with this source code,” i.e. it detects that specific license‐header phrase.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Diss
    -0.07
    .rb
    -0.06
     جي
    -0.06
    Less
    -0.06
    swers
    -0.06
     acre
    -0.06
    页
    -0.06
     bus
    -0.06
     proyecto
    -0.06
     Bangladesh
    -0.06
    POSITIVE LOGITS
     yytype
    0.07
     estão
    0.07
     están
    0.06
    říz
    0.06
    ****/↵
    0.06
     facing
    0.06
    ylv
    0.06
    existent
    0.06
    '=>
    0.06
    연
    0.06
    Act Density 0.001%

    No Known Activations